This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6034
Precision Negative: 0.8333
Recall Negative: 0.5556
F1 Negative: 0.6667
Precision Neutral: 0.75
Recall Neutral: 0.9
F1 Neutral: 0.8182
Precision Positive: 0.8462
Recall Positive: 0.7857
F1 Positive: 0.8148
Accuracy: 0.7907
Confusion Matrix: [[20, 14, 2], [2, 72, 6], [2, 10, 44]]

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Precision Negative	Recall Negative	F1 Negative	Precision Neutral	Recall Neutral	F1 Neutral	Precision Positive	Recall Positive	F1 Positive	Accuracy	Confusion Matrix
0.9478	1.0	22	0.9752	0.0	0.0	0.0	0.5064	0.9875	0.6695	0.875	0.25	0.3889	0.5407	[[0, 35, 1], [0, 79, 1], [0, 42, 14]]
0.7207	2.0	44	0.6483	0.8667	0.3611	0.5098	0.6847	0.95	0.7958	0.8913	0.7321	0.8039	0.7558	[[13, 21, 2], [1, 76, 3], [1, 14, 41]]
0.4066	3.0	66	0.6153	0.7586	0.6111	0.6769	0.7308	0.95	0.8261	1.0	0.6964	0.8211	0.7965	[[22, 14, 0], [4, 76, 0], [3, 14, 39]]
0.2355	4.0	88	0.6367	0.8	0.5556	0.6557	0.7170	0.95	0.8172	0.9756	0.7143	0.8247	0.7907	[[20, 16, 0], [3, 76, 1], [2, 14, 40]]
0.1048	5.0	110	0.5976	0.8333	0.5556	0.6667	0.75	0.9	0.8182	0.8462	0.7857	0.8148	0.7907	[[20, 14, 2], [2, 72, 6], [2, 10, 44]]
0.0745	6.0	132	0.6034	0.8333	0.5556	0.6667	0.75	0.9	0.8182	0.8462	0.7857	0.8148	0.7907	[[20, 14, 2], [2, 72, 6], [2, 10, 44]]

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

DaisyQue/finetuning-sentiment-model-distil-finalVersion

finetuning-sentiment-model-distil-finalVersion

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

DaisyQue/
finetuning-sentiment-model-distil-finalVersion